-
Notifications
You must be signed in to change notification settings - Fork 154
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Feedback upgrades #1018
Feedback upgrades #1018
Conversation
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
return groundedness_scores, {"reasons": reason} | ||
hypotheses = sent_tokenize(statement) | ||
reasons_str = "" | ||
for i, hypothesis in enumerate(tqdm( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
tqdm is here for debugging? If so, remove?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
tqdm is here to show the progress bar for feedback generation - we have this for the nli method already.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Better to not have it for either? I don't have a strong opinion
Split system and user prompt:
Enable Mistral models on Bedrock
Enable Meta models on Bedrock
Groundedness improvements (tokenizer splitting for llm-based method, add progress bar in notebook, better spacing of reason in ui)
Show usage of Together AI (LiteLLM Quickstart)
Show usage of Claude-3 (New Claude-3 Quickstart)